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

    Neuronpedia

    INDEX
    Explanations

    model code discussion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     கூறும்
    0.38
    UMIRE
    0.38
    コンサート
    0.38
    ང་
    0.37
     вку
    0.37
     aviones
    0.36
    ゞ
    0.36
     itemscope
    0.36
     gracia
    0.36
    ල
    0.36
    POSITIVE LOGITS
    patch
    0.81
     patch
    0.71
     Patch
    0.64
    Patch
    0.64
     patches
    0.57
    patches
    0.54
     PATCH
    0.52
    code
    0.51
    Code
    0.51
    diff
    0.50
    Act Density 0.001%

    No Known Activations