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

    Neuronpedia

    INDEX
    Explanations

    meta information and Bluetooth Connectivity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trustees
    0.77
     colaborar
    0.77
     liberals
    0.74
    ね
    0.74
    𝐌
    0.74
     respecter
    0.73
     derogatory
    0.73
     wirken
    0.72
    omaly
    0.71
     sanctioned
    0.71
    POSITIVE LOGITS
    entino
    0.78
    easily
    0.72
    zones
    0.71
    ఢ
    0.67
    üre
    0.67
     Static
    0.66
    Artifact
    0.66
     recomb
    0.66
    creat
    0.66
     Saw
    0.66
    Act Density 0.002%

    No Known Activations