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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fist
    -0.07
     yatırım
    -0.06
    イト
    -0.06
     vegan
    -0.06
     Saturn
    -0.06
     itm
    -0.06
    .unshift
    -0.06
    _sy
    -0.06
     noises
    -0.06
     documentaries
    -0.06
    POSITIVE LOGITS
    pom
    0.07
    ΙΔ
    0.06
    Hardware
    0.06
     glUniform
    0.06
     intimidating
    0.06
    Mind
    0.06
    anken
    0.06
    offer
    0.06
    lost
    0.06
    τιο
    0.06
    Act Density 0.011%

    No Known Activations