Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of class instantiation or memory allocation in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    `self` in code or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.69
    ieteur
    -0.66
    ="@+
    -0.65
    msgTypes
    -0.65
     snippetHide
    -0.65
     Infórmanos
    -0.61
    <bos>
    -0.59
    MigrationBuilder
    -0.58
     createSlice
    -0.58
    +:+
    -0.57
    POSITIVE LOGITS
    self
    0.76
    Self
    0.55
     self
    0.55
     Wissenschaft
    0.54
    niosek
    0.53
     Self
    0.51
     Hidup
    0.49
     Zugriff
    0.47
     Gesellschaft
    0.47
    SELF
    0.47
    Act Density 0.001%

    No Known Activations